Related papers: A Unified Speaker Adaptation Method for Speech Syn…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker.…

In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…

There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based…

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Controllable speech synthesis aims to control the style of generated speech using reference input, which can be of various modalities. Existing face-based methods struggle with robustness and generalization due to data quality constraints,…

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target reference speech can be used. Out-of-domain transfer is still a…

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for…

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition,…

We present SVCnet, a system for modelling speaker variability. Encoder Neural Networks specialized for each speech sound produce low dimensionality models of acoustical variation, and these models are further combined into an overall model…

The single-speaker singing voice synthesis (SVS) usually underperforms at pitch values that are out of the singer's vocal range or associated with limited training samples. Based on our previous work, this work proposes a…

Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

In this paper, we describe a statistical parametric speech synthesis approach with unit-level acoustic representation. In conventional deep neural network based speech synthesis, the input text features are repeated for the entire duration…

Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often modeled separately. Here, we test how encoding and decoding…